Omnigent is an open-source orchestration layer for running and coordinating different AI coding agents through one system. It is for developers who want to combine agents, apply policies and sandboxing, and continue sessions across devices. The catalogue add-ons extend its agent workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add omnigent-ai/omnigent --skill resolve-drive-prgit clone --depth 1 https://github.com/omnigent-ai/omnigentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/omnigent-ai/omnigent/resolve-drive-pr)<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/resolve-drive-pr"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/resolve-drive-pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/resolve-drive-pr"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/resolve-drive-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.01636 |
| Opus 5.5 | $0.00010 | $0.00654 |
| Sonnet 5 | $0.00005 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
resolve-drive-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive an open PR
Read each resource when reaching its substep, preserving the publication mode:
| Substep | Resource |
|---|---|
| 4.2, current CI and mergeability | ci.md |
| 4.3, independent Polly review | polly.md |
| 4.1, preview after CI and Polly are clean | preview.md |
| 4.4, live-validation instructions | validation-prompt.md |
| 4.5, final review and maintainer handoff | final-review.md |
Use read_skill_file with this skill name and the relative filename, or read
relative to the directory supplied by the native Skill tool. Workflow-owned
author runs read only validation-prompt.md for deferred body preparation;
local-only author runs skip this skill. Review-remediation follows its mode's
exemptions. Load resolve-handoff before any interim or final handoff.
Step 4 — Land the PR: preview, green CI, clean review, hand it to the maintainer
This step applies to any PR you are driving toward landable — the one you
opened (author path, Step 2B/3) and the existing PR you reviewed and kept as
the fix (review path, Step 2A, when its approach was sound). The goal is identical
either way: a live preview, green CI, a clean automated review, a copy-paste
live-validation command, and a maintainer tagged. skip_push runs (author path
that only committed locally) have no PR to land, so skip Step 4 entirely.
Workflow-owned author runs also have no PR during the agent session: perform only
the deferred body/prompt preparation called out in Step 4.4 before the final
handoff, and leave preview, CI, Polly, GitHub comments, and maintainer tagging to
the post-publication workflow. Once a directly published or reviewed PR is up you
stay on it until CI is green and the review is clean, then hand it to a
human. The sub-steps overlap in time (kick off the preview and the first review,
then poll), so don't serialize what can run concurrently.
Refresh the shared impact assessment after changes made in this loop, including CI/review fixes and conflict resolution. Earlier green checks do not cover a new head automatically.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 107 lines · 24 tokens per session scan A 1bbee886eeb8
resolve-drive-pr is a skill published in the GitHub repository omnigent-ai/omnigent (10,212 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 1,636 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other skills, from other repositories
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
understand-pr
Review a PR the way a seasoned maintainer would — build an independent model before seeing the diff, investigate the implementation and history, verify material claims, and return a concise briefing. Use for any PR review, self-review, or re-review.
factory-gitlab-review
Review a GitLab merge request for a Factory work item using brokered source-control tools.
factory-gitlab-rereview
Re-review a GitLab merge request after new commits and reconcile the previous review.